arXiv 1807.044182018-07cs.CV

Subsampled Turbulence Removal Network

The Chinese University of Hong Kong（香港中文大学）

Wai Ho Chak, Chun Pong Lau, Lok Ming Lui

英文摘要：

We present a deep-learning approach to restore a sequence of turbulence-distorted video frames from turbulent deformations and space-time varying blurs. Instead of requiring a massive training sample size in deep networks, we purpose a training strategy that is based on a new data augmentation method to model turbulence from a relatively small dataset. Then we introduce a subsampled method to enhance the restoration performance of the presented GAN model. The contributions of the paper is threefold: first, we introduce a simple but effective data augmentation algorithm to model the turbulence in real life for training in the deep network; Second, we firstly purpose the Wasserstein GAN combined with $\ell_1$ cost for successful restoration of turbulence-corrupted video sequence; Third, we combine the subsampling algorithm to filter out strongly corrupted frames to generate a video sequence with better quality.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

基于扩散模型的概率先验驱动注意力机制用于大气湍流成像

Probabilistic Prior Driven Attention Mechanism Based on Diffusion Model for Imaging Through Atmospheric Turbulence

Northwestern Polytechnical University（西北工业大学）；Beihang University（北京航空航天大学）

针对大气湍流导致的图像畸变，提出PPTRN网络，结合DDPM先验建模与Transformer特征提取，通过两阶段训练和概率先验驱动交叉注意力机制减少伪影，显著提升复原质量并树立新基准。

2024-11-15cs.CV

Restoration of Atmospheric Turbulence-distorted Images via RPCA and Quasiconformal Maps

We address the problem of restoring a high-quality image from an observed image sequence strongly distorted by atmospheric turbulence. A novel algorithm is proposed in this paper to reduce geometric distortion as well as space-and-time-varying blur due to strong turbulence. By considering a suitable energy functional, our algorithm first obtains a sharp reference image and a subsampled image sequence containing sharp and mildly distorted image frames with respect to the reference image. The subsampled image sequence is then stabilized by applying the Robust Principal Component Analysis (RPCA) …

2017-09-19cs.CGcs.CVcs.GR

EvTurb：事件相机引导的湍流消除

EvTurb: Event Camera Guided Turbulence Removal

State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学）；National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（视觉技术国家工程研究中心，计算机学院，北京大学）

本文提出事件引导的湍流消除框架EvTurb，通过两步事件引导网络解耦模糊与倾斜畸变，并构建首个真实湍流数据集TurbEvent，在保持计算效率下超越现有方法。

2025-08-14cs.CV

MAMAT：基于3D Mamba的大气湍流消除及其目标检测能力

MAMAT: 3D Mamba-Based Atmospheric Turbulence Removal and its Object Detection Capability

University of Bristol（布里斯托大学）

针对大气湍流导致的监控视频质量下降问题，提出基于3D Mamba的双模块MAMAT方法，通过可变形3D卷积配准和细节增强，在视觉质量和目标检测精度上均优于现有学习方法。

2025-03-22cs.CV

大气湍流消除的深度学习技术：综述

Deep Learning Techniques for Atmospheric Turbulence Removal: A Review

The University of Bristol（布里斯托大学）

本文综述了大气湍流对图像的影响，并对比了 Transformers、SWIN 和 Mamba 等深度神经网络在消除时空图像扭曲方面的性能，指出深度学习比常规方法更高效且适用于小型设备。

2024-09-03astro-ph.IMcs.CV

Atmospheric Turbulence Removal with Complex-Valued Convolutional Neural Network

University of Bristol（布里斯托大学）

Atmospheric turbulence distorts visual imagery and is always problematic for information interpretation by both human and machine. Most well-developed approaches to remove atmospheric turbulence distortion are model-based. However, these methods require high computation and large memory making real-time operation infeasible. Deep learning-based approaches have hence gained more attention but currently work efficiently only on static scenes. This paper presents a novel learning-based framework offering short temporal spanning to support dynamic scenes. We exploit complex-valued convolutions as …

2022-05-09cs.CVcs.MMeess.IV

更多相关论文收起更多论文

Distortion-driven Turbulence Effect Removal using Variational Model

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Technology, Sydney（悉尼科技大学）；Xiamen University（厦门大学）

It remains a challenge to simultaneously remove geometric distortion and space-time-varying blur in frames captured through a turbulent atmospheric medium. To solve, or at least reduce these effects, we propose a new scheme to recover a latent image from observed frames by integrating a new variational model and distortion-driven spatial-temporal kernel regression. The proposed scheme first constructs a high-quality reference image from the observed frames using low-rank decomposition. Then, to generate an improved registered sequence, the reference image is iteratively optimized using a varia…

2014-01-17cs.CV

Atmospheric turbulence removal using convolutional neural network

University of Bristol（布里斯托大学）

This paper describes a novel deep learning-based method for mitigating the effects of atmospheric distortion. We have built an end-to-end supervised convolutional neural network (CNN) to reconstruct turbulence-corrupted video sequence. Our framework has been developed on the residual learning concept, where the spatio-temporal distortions are learnt and predicted. Our experiments demonstrate that the proposed method can deblur, remove ripple effect and enhance contrast of the video sequences simultaneously. Our model was trained and tested with both simulated and real distortions. Experimental…

2019-12-22cs.CVcs.LGeess.IV

利用视频序列深度视觉先验去除大气湍流

Atmospheric Turbulence Removal with Video Sequence Deep Visual Priors

University of Bristol（布里斯托尔大学）

针对大气湍流导致的图像畸变及现有方法的运动伪影、数据依赖问题，提出基于加速DIP并融合像素混排与时间滑动窗口的自监督时空先验方法，可在无需外部数据集和真值的情况下提升原始或预处理视频序列的视觉质量。

2024-02-29cs.AIcs.CVeess.IV

Variational models for joint subsampling and reconstruction of turbulence-degraded images

The Chinese University of Hong Kong（香港中文大学）

Turbulence-degraded image frames are distorted by both turbulent deformations and space-time-varying blurs. To suppress these effects, we propose a multi-frame reconstruction scheme to recover a latent image from the observed image sequence. Recent approaches are commonly based on registering each frame to a reference image, by which geometric turbulent deformations can be estimated and a sharp image can be restored. A major challenge is that a fine reference image is usually unavailable, as every turbulence-degraded frame is distorted. A high-quality reference image is crucial for the accurat…

2017-12-08cs.CV

Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs

Whiting School of Engineering, Johns Hopkins University（约翰斯·霍普金斯大学惠廷工程学院）

Atmospheric turbulence significantly affects imaging systems which use light that has propagated through long atmospheric paths. Images captured under such condition suffer from a combination of geometric deformation and space varying blur. We present a deep learning-based solution to the problem of restoring a turbulence-degraded face image where prior information regarding the amount of geometric distortion and blur at each location of the face image is first estimated using two separate networks. The estimated prior information is then used by a network called, Turbulence Distortion Removal…

2020-07-16cs.CV

CVPR 2023 UG$^{\ extbf{2}}$+ 挑战赛赛道2.1——大气湍流下文本识别第一名解决方案

1st Solution Places for CVPR 2023 UG$^{\textbf{2}}$+ Challenge Track 2.1-Text Recognition through Atmospheric Turbulence

Huazhong University of Science and Technology（华中科技大学）

本研究提出多阶段湍流图像恢复框架，通过帧选择、光流配准、DT-CWT区域融合和学习去伪影处理失真帧，在CVPR 2023 UG²+挑战赛湍流下文本识别任务中获准确率第一。

2023-06-15cs.CV

CVPR 2023 UG$^2$+挑战赛赛道2.2——大气湍流下编码目标恢复的第一名解决方案

1st Solution Places for CVPR 2023 UG$^2$+ Challenge Track 2.2-Coded Target Restoration through Atmospheric Turbulence

Huazhong University of Science and Technology（华中科技大学）

本研究提出一种多阶段大气湍流编码目标恢复框架，经配准、帧选择平均、学习去模糊及后处理，在CVPR 2023 UG²+赛道2.2中夺冠。

2023-06-15cs.CV